Zippy & The Professor

Unlocking the Secret of Super-Speed Reading!

cloud

Meet the Team

Inside every super-smart computer, there's a team working hard to write stories for you.

school

Professor Prose

The Target Model. He is super smart and never makes a mistake. But... he is very slow. He writes one... word... at... a... time.

rocket_launch

Zippy

The Draft Model. She is small, full of energy, and loves to guess! She's super fast, but sometimes her guesses are a little silly.

The Problem: The Slow Writer

timer

Normally, computers write like Professor Prose. To write a sentence, the Professor has to think really hard about the first word, write it down, then think about the next one, and so on.

It's perfect, but it takes FOREVER!

The Solution: The Guessing Game!

lightbulb

What if Zippy helps? While the Professor is busy checking the first word, Zippy guesses the next 3 words!

Then, the Professor just looks at Zippy's list and says "Yes, Yes, Yes!" or "No, try again." Checking a list is much faster than writing from scratch!

This is called Speculative Decoding!

Interactive Lab

The Speedy Storyteller Race

See the difference between "Normal" and "Speculative" speed!

videogame_asset SIMULATION CONTROL

Select a mode below to start writing...

person

The Slow Way

Professor Prose works alone. Accurate but slow.

play_circle

groups

The Speculative Way

Zippy guesses, Professor checks! Much faster.

Zippy's Guess Length: 3 words

play_circle

Time Taken

0.0s

Steps (Validations)

Tokens/Sec

Why is it faster?

Without Speculative Decoding

Professor Prose picks up one block (word), checks it, puts it down. Then walks back to get the next one.

With Speculative Decoding

Zippy hands the Professor a whole tray of 3 blocks! The Professor checks them all at once. One trip instead of three!